© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11483
    Prev
    Next
    INDEX
    Explanations

    operator actions and body parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buen
    -1.02
     service
    -0.97
     Figuren
    -0.94
     llega
    -0.93
     бампер
    -0.92
    ysteine
    -0.88
     العديد
    -0.88
     Interesse
    -0.87
     меда
    -0.87
    糶
    -0.86
    POSITIVE LOGITS
     vong
    1.07
     gjorde
    1.06
     dedans
    1.04
     personlig
    1.01
     boî
    0.99
    monger
    0.98
     couvercle
    0.98
     chè
    0.96
     himself
    0.94
     Dott
    0.94
    Activations Density 0.051%

    No Known Activations